GeCo: A Differentiable Geometric Consistency Metric for Video Generation

• URL: http://arxiv.org/abs/2512.22274v1
• Date: Thu, 25 Dec 2025 03:28:28 GMT
• Title: GeCo: A Differentiable Geometric Consistency Metric for Video Generation
• Abstract summary: We introduce GeCo, a geometry-grounded metric for jointly detecting geometric deformation and occlusion-inconsistency artifacts in static scenes.<n>By fusing residual motion and depth priors, GeCo produces interpretable, dense consistency maps that reveal these artifacts.<n>We use GeCo to systematically benchmark recent video generation models, uncovering common failure modes, and further employ it as a training-free loss guidance to reduce deformation artifacts during video generation.
• Score: 61.28264035357065
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce GeCo, a geometry-grounded metric for jointly detecting geometric deformation and occlusion-inconsistency artifacts in static scenes. By fusing residual motion and depth priors, GeCo produces interpretable, dense consistency maps that reveal these artifacts. We use GeCo to systematically benchmark recent video generation models, uncovering common failure modes, and further employ it as a training-free guidance loss to reduce deformation artifacts during video generation.

Related papers

• VideoWeave: Unlocking Geometric Consistency in Video Generation via Joint Geometry-Video Modeling [49.98112719317813]
  Video diffusion models often fail to preserve 3D structure over time.<n>Existing methods usually enforce geometric consistency by using explicit geometry reconstructions.<n>We propose VideoWeave, a latent-space post-training framework that uses implicit geometry-model features to constrain the generative distribution.
  arXiv  Detail & Related papers  (2026-06-12T06:41:13Z)
• GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation [46.507099021313074]
  We introduce a geometry-consistency reward that measures whether motion in a generated video is compatible with a coherent scene.<n>We operationalize this using optical flow, depth--pose predictions, and feature-based correspondence to separate rigid and dynamic regions.<n>Experiments show substantial reductions in temporal geometric artifacts over strong baselines while preserving perceptual quality.
  arXiv  Detail & Related papers  (2026-05-18T13:17:08Z)
• Quantitative Video World Model Evaluation for Geometric-Consistency [18.53748808467407]
  Generative video models are increasingly studied as implicit world models.<n> evaluating whether they produce physically plausible 3D structure and motion remains challenging.<n>We introduce PDI-Bench, a framework for auditing geometric coherence in generated videos.
  arXiv  Detail & Related papers  (2026-05-14T17:59:04Z)
• Measuring 3D Spatial Geometric Consistency in Dynamic Generated Videos [67.7364297817535]
  We introduce SGC, a metric for evaluating 3D textbfSpatial textbfGeometric textbfConsistency in videos.<n>SGC robustly quantifies geometric inconsistencies, effectively identifying critical failures missed by existing metrics.
  arXiv  Detail & Related papers  (2026-03-19T15:44:39Z)
• Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video [76.32954467706581]
  We propose SAGE, a framework for Scalable Adaptation of GEometric foundation models from raw video streams.<n>We use a hierarchical mining pipeline to transform videos into training trajectories and hybrid supervision.<n>Experiments show that SAGE significantly enhances zero-shot generalization, reducing Chamfer Distance by 20-42% on unseen benchmarks.
  arXiv  Detail & Related papers  (2026-02-08T09:53:21Z)
• Geometry-Aware Rotary Position Embedding for Consistent Video World Model [48.914346802616414]
  ViewRope is a geometry-aware encoding that injects camera-ray directions directly into video transformer self-attention layers.<n>Geometry-Aware Frame-Sparse Attention exploits these geometric cues to selectively attend to relevant historical frames.<n>Our results demonstrate that ViewRope substantially improves long-term consistency while reducing computational costs.
  arXiv  Detail & Related papers  (2026-02-08T08:01:16Z)
• GeoVideo: Introducing Geometric Regularization into Video Generation Model [46.38507581500745]
  We introduce geometric regularization losses into video generation by augmenting latent diffusion models with per-frame depth prediction.<n>Our method bridges the gap between appearance generation and 3D structure modeling, leading to improved structural coherence-temporal shape, consistency, and physical plausibility.
  arXiv  Detail & Related papers  (2025-12-03T05:11:57Z)
• Epipolar Geometry Improves Video Generation Models [73.44978239787501]
  3D-consistent video generation could significantly impact numerous downstream applications in generation and reconstruction tasks.<n>We explore how epipolar geometry constraints improve modern video diffusion models.<n>By bridging data-driven deep learning with classical geometric computer vision, we present a practical method for generating spatially consistent videos.
  arXiv  Detail & Related papers  (2025-10-24T16:21:37Z)
• Visibility-Aware Densification for 3D Gaussian Splatting in Dynamic Urban Scenes [7.253732091582086]
  VAD-GS is a 3DGS framework tailored for geometry recovery in challenging urban scenes.<n>Our method identifies unreliable geometry structures via voxel-based visibility reasoning.<n>It selects informative supporting views through diversity-aware view selection, and recovers missing structures via patch matching-based stereo reconstruction.
  arXiv  Detail & Related papers  (2025-10-10T13:22:12Z)
• GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors [47.21120442961684]
  We propose GeometryCrafter, a novel framework that recovers high-fidelity point map sequences with temporal coherence from open-world videos.<n>We show that GeometryCrafter achieves state-of-the-art 3D accuracy, temporal consistency, and generalization capability.
  arXiv  Detail & Related papers  (2025-04-01T17:58:03Z)
• The Drunkard's Odometry: Estimating Camera Motion in Deforming Scenes [79.00228778543553]
  This dataset is the first large set of exploratory camera trajectories with ground truth inside 3D scenes. Simulations in realistic 3D buildings lets us obtain a vast amount of data and ground truth labels. We present a novel deformable odometry method, dubbed the Drunkard's Odometry, which decomposes optical flow estimates into rigid-body camera motion.
  arXiv  Detail & Related papers  (2023-06-29T13:09:31Z)
• Consistent Video Depth Estimation [57.712779457632024]
  We present an algorithm for reconstructing dense, geometrically consistent depth for all pixels in a monocular video. We leverage a conventional structure-from-motion reconstruction to establish geometric constraints on pixels in the video. Our algorithm is able to handle challenging hand-held captured input videos with a moderate degree of dynamic motion.
  arXiv  Detail & Related papers  (2020-04-30T17:59:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.